Time series analysis uses statistical techniques to determine how a sequence of numerical data points varies during a specific period of time. For example, time series analysis is used in the financial sector to track the prices of securities, commodities, and other assets to discover how they may vary seasonally. These techniques are important in business, science, public opinion polling, or any other field which seeks to understand how things change over time.
The insights from time series analysis are often used for time series forecasting, which seeks predictions in the future changes in the value of a variable based on its movement in the past. Financial modeling and other applications of these techniques may also use linear regression to establish relationships between the variable of interest and other variables, such as overall economic factors like the unemployment rate or weather patterns.
Even more powerful prediction engines can be developed using machine learning and deep learning approaches. The use of TensorFlow, R, and Python programming for increasingly sophisticated applications of time series analysis is making it possible to uncover complex patterns in vast datasets that would have been impossible - or, at least, very difficult and time-consuming - in the not-too-distant past.